😃 Welcome to my personal page!
I am Tianqi Liu (刘天齐 in Chinese), a first year (2023.09-) master’s student in Artificial Intelligence at Huazhong University of Science and Technology (HUST), supervised by Prof. Zhiguo Cao. Before that, I received my bachelor’s degree from HUST in 2023. My current research interests is 3D vision, working on fast and high-quality 3D reconstructions. To achieve this, my current main research areas include Multi-View Stereo (MVS), Neural Radiance Field (NeRF), and 3D Gaussian Splatting (3D-GS).
🔥 News
- 2024-02 : 🎉 GeFu and RStab are accepted to CVPR 2024.
- 2023-07 : 🎉 ET-MVSNet and DMVSNet are accepted to ICCV 2023.
📝 Publications
![sym](images/MVSGaussian.png)
[arXiv 2024] Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo
Tianqi Liu, Guangcong Wang, Shoukang Hu, Liao Shen, Xinyi Ye, Yuhang Zang, Zhiguo Cao, Wei Li, Ziwei Liu.
[Project page]
[Paper]
[Code]
[Video]
MVSGaussian is a Gaussian-based method designed for efficient reconstruction of unseen scenes from sparse views in a single forward pass. It offers high-quality initialization for fast training and real-time rendering.
![sym](images/gefu.png)
[CVPR 2024] Geometry-aware Reconstruction and Fusion-refined Rendering for Generalizable Neural Radiance Fields
Tianqi Liu, Xinyi Ye, Min Shi, Zihao Huang, Zhiyu Pan, Zhan Peng, Zhiguo Cao.
[Project page]
[Paper]
[Code]
[Video]
We present GeFu, a generalizable NeRF method that synthesizes novel views from multi-view images in a single forward pass.
![sym](images/RStab.png)
[CVPR 2024] 3D Multi-frame Fusion for Video Stabilization
Zhan Peng, Xinyi Ye, Weiyue Zhao, Tianqi Liu, Huiqiang Sun, Baopu Li, Zhiguo Cao.
[Paper]
[Code]
RStab is a novel framework for video stabilization that integrates 3D multi-frame fusion through volume rendering.
![sym](images/ETMVSNet.png)
[ICCV 2023] When Epipolar Constraint Meets Non-local Operators in Multi-View Stereo
Tianqi Liu, Xinyi Ye, Weiyue Zhao, Zhiyu Pan, Min Shi, Zhiguo Cao.
[Paper]
[Code]
ETMVSNet uses epipolar geometric priors to constrain feature aggregation fileds, thereby efficiently inferring multi-view depths and reconstructing scenes.
![sym](images/dmvsnet.png)
[ICCV 2023] Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells
Xinyi Ye, Weiyue Zhao, Tianqi Liu, Zihao Huang, Zhiguo Cao, Xin Li.
[Paper]
[Code]
DMVSNet proposes a new perspective to consider the depth geometry of multi-view stereo and introduces a dual-depth approach to approximate the depth geometry with saddle-shaped cells.
🎖 Honors and Awards
- 2023 Honours Degrees (Top 3%)
- 2022 National Scholarship (Top 2%)
- 2022 Merit Student (Top 2%)
- 2022 Meritorious Winner, American College Students Mathematical Contest in Modeling
- 2021 Outstanding Undergraduate Student (Top 2%)
- 2021 First prize in the National Mathematics Competition for college students